Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
llm-internals
AI repositoriesLearn LLM internals step by step - from tokenization to attention to inference optimization.
git clone https://github.com/amitshekhariitbhu/llm-internals.git -
Qwen
AI repositoriesThe official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
git clone https://github.com/QwenLM/Qwen.git -
sglang
AI repositoriesSGLang is a high-performance serving framework for large language models and multimodal models.
git clone https://github.com/sgl-project/sglang.git -
InternLM
AI repositoriesOfficial release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
git clone https://github.com/InternLM/InternLM.git -
LLMs-from-scratch
AI repositoriesImplement a ChatGPT-like LLM in PyTorch from scratch, step by step
git clone https://github.com/rasbt/LLMs-from-scratch.git -
Chinese-LLaMA-Alpaca-2
AI repositories中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
git clone https://github.com/ymcui/Chinese-LLaMA-Alpaca-2.git -
daam
AI repositoriesDiffusion attentive attribution maps for interpreting Stable Diffusion.
git clone https://github.com/castorini/daam.git -
pegainfer
AI repositoriesPure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
git clone https://github.com/pegainfer-project/pegainfer.git -
kimi-k3-in-c
AI repositoriesA 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
git clone https://github.com/FareedKhan-dev/kimi-k3-in-c.git -
oneDNN
AI repositoriesOpen-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
git clone https://github.com/uxlfoundation/oneDNN.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.